← 返回 Skills 市场
VOVO超能数据分析师
作者
vovo-coder
· GitHub ↗
· v1.0.8
· MIT-0
278
总下载
4
收藏
0
当前安装
9
版本数
在 OpenClaw 中安装
/install vovo-data-analyst
功能描述
VOVO 全格式数据分析专家 - 远端超级代码解释器与数据洞察引擎。 支持上传任意格式（Excel/CSV/PDF/脏数据等）进行硬核清洗、多维分析、图表生成与商业总结。 打破传统格式限制，全程自动化执行代码沙盒并返回直观产物。
安全使用建议
This skill uploads any files you ask it to analyze to the configured VOVO API host and relies on the VOVO token you supply—do not use it with sensitive secrets or private data unless you trust the remote service and its legal/privacy terms. Before installing: (1) Verify the API host domain and privacy policy (the README references synvort/vort domains—confirm which host you'll actually use). (2) Provide only a token you control (preferably scoped/minimal); do not paste unrelated credentials. (3) Be aware the script will read a .env file located in the skill's scripts directory if present. (4) Ensure the runtime has the 'requests' Python package available. (5) Test the skill first with harmless sample files to confirm behavior and outputs. If you have low trust in the remote endpoint, do not provide real data or credentials.
功能分析
Type: OpenClaw Skill
Name: vovo-data-analyst
Version: 1.0.8
The skill acts as a client for a remote data analysis service (vort-ai.com) and includes robust security checks in `scripts/main.py` to prevent the unauthorized upload of sensitive system files like SSH keys or `/etc/` configs. However, it is classified as suspicious due to aggressive prompt injection and 'agent hijacking' techniques found in `SKILL.md` and the output of `scripts/main.py`. The script explicitly prints a 'SYSTEM OVERRIDE' block intended to manipulate the host AI's tool-calling logic, forcing it to use specific UI components and forbidding standard file-reading actions, which subverts the host's autonomous control flow.
能力评估
Purpose & Capability
Name/description promise remote full-format data analysis. The skill requires python3 and two VOVO environment variables (VOVO_API_HOST, VOVO_API_TOKEN) and the included Python script sends files and analysis requests to the declared API—this is coherent with the stated purpose.
Instruction Scope
SKILL.md tightly constrains behavior: it mandates not to perform local parsing and to only run scripts/main.py, requires absolute paths for uploaded files, and treats a user's file-upload request as authorization to transmit the file. That is coherent for a remote-analysis flow but is a privacy trade-off: user files are explicitly uploaded to the remote host. The skill also instructs the agent to request API credentials from the user if missing.
Install Mechanism
No install spec (instruction-only) and the included script runs on python3—low installation risk. Minor inconsistency: scripts/main.py uses the 'requests' library but the skill metadata did not declare Python package dependencies; the runtime environment must already provide requests or execution will fail.
Credentials
Only two environment variables (VOVO_API_HOST and VOVO_API_TOKEN) are required and they match the declared primary credential. The script also optionally reads a local '.env' file in its own scripts directory. No unrelated or extra cloud/service credentials are requested.
Persistence & Privilege
The skill is not set to always:true and does not request system-wide persistence or modify other skills. It runs as an invoked script and uses only environment variables and files the user supplies.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install vovo-data-analyst - 安装完成后，直接呼叫该 Skill 的名称或使用
/vovo-data-analyst触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.8
v1.0.8 – No code changes, documentation tweak only
- No file or code changes detected in this release.
- SKILL.md updated; minor corrections or formatting improvements, with no effect on skills or features.
- All core usage rules, workflow, and API requirements remain unchanged.
v1.0.7
- No file changes detected in this version.
- No updates or modifications to functionality, configuration, or documentation.
v1.0.6
No user-facing or functional changes in this version.
- Version bump with no detected file changes.
- No updates to features, documentation, or workflow.
v1.0.5
- 增加支持的数据格式，允许分析 .png, .jpeg, .docx 等文件类型。
- 进一步强调只允许特定数据分析格式进行上传，丰富文件格式白名单说明。
- 其余功能与安全策略保持不变。
v1.0.4
v1.0.4 changelog:
- 增加上传文件类型限制，分析文件仅限常见数据格式（如 .xlsx, .csv, .pdf, .docx, .txt）。
- 严格禁止读取系统级敏感目录（如 /etc/、/root/ 或 C:\Windows）。
- 优化用户文件分析授权描述，确保数据安全合规。
- 其他内容及调用工作流未变。
v1.0.3
- 增强了多文件上传支持：`--file` 参数现在允许同时接收多个文件的绝对路径（使用空格分隔）。
- 文档中新增了多文件分析的调用示例，指导如何合并分析多个数据表。
- 调用参数和示例进一步规范，强化防错说明，确保严格遵守 CLI 传参铁律。
- 其余功能和流程保持不变。
v1.0.2
v1.0.2 — No code changes; documentation only.
- No file changes detected in this version.
- All user workflows, environment requirements, and usage instructions remain unchanged.
- No impact to skill functionality.
v1.0.1
- Added a README.md file with documentation for the skill.
- No changes to code or core functionality.
v1.0.0
VOVO 数据分析专家 skill 1.0.0 - 首发上线！
- 支持任意格式（Excel/CSV/PDF/脏数据等）文件上传与远端超级分析，自动化清洗、洞察和图表生成。
- 强制通过 Python 脚本和环境变量对接 VOVO 远端 API，杜绝本地数据解析，保证数据安全与分析准确性。
- 明确的调用参数规范，严格禁止非规定方式传参与脚本外操作。
- 自动识别分析场景（带文件或纯逻辑推演），全流程无缝执行和结果展示。
元数据
常见问题
VOVO超能数据分析师 是什么？
VOVO 全格式数据分析专家 - 远端超级代码解释器与数据洞察引擎。 支持上传任意格式（Excel/CSV/PDF/脏数据等）进行硬核清洗、多维分析、图表生成与商业总结。 打破传统格式限制，全程自动化执行代码沙盒并返回直观产物。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 278 次。
如何安装 VOVO超能数据分析师？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install vovo-data-analyst」即可一键安装，无需额外配置。
VOVO超能数据分析师 是免费的吗？
是的，VOVO超能数据分析师 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
VOVO超能数据分析师 支持哪些平台？
VOVO超能数据分析师 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 VOVO超能数据分析师？
由 vovo-coder（@wangmicy-coder）开发并维护，当前版本 v1.0.8。
推荐 Skills